Efficient Facial Expression Analysis For Dimensional Affect Recognition Using Geometric Features
This work addresses the need for efficient and robust affect recognition in real-life situations, though it is incremental as it builds on existing geometric feature methods.
The authors tackled the problem of dimensional affect recognition by introducing a facial expression analysis system based on geometric features and PLS regression, achieving comparable performance to deep learning models with significantly lower computational resources.
Despite their continued popularity, categorical approaches to affect recognition have limitations, especially in real-life situations. Dimensional models of affect offer important advantages for the recognition of subtle expressions and more fine-grained analysis. We introduce a simple but effective facial expression analysis (FEA) system for dimensional affect, solely based on geometric features and Partial Least Squares (PLS) regression. The system jointly learns to estimate Arousal and Valence ratings from a set of facial images. The proposed approach is robust, efficient, and exhibits comparable performance to contemporary deep learning models, while requiring a fraction of the computational resources.